Promptfoo Evals plugin: what it installs and how to add it
Guides AI coding agents in building and maintaining promptfoo evaluation suites with assertions, provider patterns and CI-friendly tests.
From the Marketplace: claude-community marketplace
Install
> /plugin marketplace add anthropics/claude-plugins-community> /plugin install promptfoo-evals@claude-communityRun both lines inside Claude Code: the first adds the marketplace, the second installs the plugin.
About this plugin
Use it when an AI coding agent needs to create or maintain promptfoo evaluation suites. It promotes deterministic assertions first, file-based test organisation, correct environment-variable syntax, and checks for hallucination and faithfulness.
The guidance includes a cheatsheet covering more than 30 assertion types, provider patterns for OpenAI, Anthropic, Google, Bedrock, HTTP, Python and JavaScript, plus patterns for JSON validation, dataset-driven scaling and CI-friendly runs.
What's inside
- 0 skills
- 0 slash commands
- 0 agents
- 0 hooks
- 0 MCP servers
More from claude-community
- CavemanCompresses coding-agent messages while preserving technical terms, code, commands, and exact errors.Marketplace: claude-communityGitHub stars: 109k
- Understand AnythingAnalyses codebases and documents into an interactive knowledge graph for exploring files, symbols, dependencies, and project structure.Marketplace: claude-communityGitHub stars: 85k
- ImpeccableAdds design vocabulary and review guidance for building clearer, more consistent frontend interfaces with AI coding agents.Marketplace: claude-communityGitHub stars: 73.7k
- Mem0Adds persistent, scoped memory to Claude for retaining preferences, project context, and conversation history across sessions.Marketplace: claude-communityGitHub stars: 66.4k
- Last 30 DaysSearches recent online discussions and sources to produce a structured 30-day digest on any topic.Marketplace: claude-communityGitHub stars: 63.4k
- Marketing SkillsAdds 50 marketing skills for AI agents covering conversion optimisation, copywriting, SEO, paid ads and growth.Marketplace: claude-communityGitHub stars: 52.2k
Related plugins
- SuperpowersOfficialGuides Claude Code through planning, TDD, debugging, code review, and subagent-driven software development.Marketplace: claude-plugins-officialGitHub stars: 294k
- Matt Pocock SkillsOfficialAdds reusable engineering skills for specification, TDD, code review, debugging, domain modelling and project handoffs.Marketplace: claude-plugins-officialGitHub stars: 274k
- Understand AnythingAnalyses codebases and documents into an interactive knowledge graph for exploring files, symbols, dependencies, and project structure.Marketplace: claude-communityGitHub stars: 85k
- Chrome DevTools MCPOfficialControls and inspects a live Chrome browser for debugging, performance analysis, network checks, and Puppeteer automation.Marketplace: claude-plugins-officialGitHub stars: 52.9k
Skills, not plugins
Prefer a single skill for development work? 471 skills in the same category, each installed on its own.